Move From Data to Machine Learning Solutions
Building useful Machine Learning solutions requires more than knowing how to import a library or run an algorithm. Learn to understand programming, numerical computation, data preparation, statistics, model development, and evaluation — and build solutions that can be evaluated and improved.
- Structured ML learning pathway
- Practical industry projects
- Python, NumPy, Pandas, statistics
- Study Buddies and collaborative learning
- Portfolio development
Go Beyond Understanding Data, Learn to Build Systems That Learn From It.
Organizations generate enormous amounts of data, but identifying patterns and making predictions from that information can require more than traditional analysis.
Machine Learning provides techniques that allow computers to learn patterns from data and use those patterns to make predictions, classify information, identify groups, and support automated decisions.
These problems require an understanding of data, algorithms, modeling techniques, and evaluation.
In this Study Group, you will learn to approach Machine Learning as a complete technical process.
Understand patterns
Learn how algorithms identify patterns and relationships within datasets.
Prepare data for modeling
Clean, transform, encode, and organize data before training a model.
Develop predictive models
Apply appropriate algorithms to regression and classification problems.
Discover hidden structures
Use clustering and dimensionality reduction to investigate patterns in unlabeled data.
Evaluate model performance
Understand whether a model performs well and whether its predictions are reliable.
Improve models
Investigate overfitting, underfitting, feature selection, cross-validation, and hyperparameter tuning.
What will you learn to do?
Understand patterns
Learn how algorithms identify patterns and relationships within datasets.
Prepare data for modeling
Clean, transform, encode, and organize data before training a model.
Develop predictive models
Apply appropriate algorithms to regression and classification problems.
Discover hidden structures
Use clustering and dimensionality reduction to investigate patterns in unlabeled data.
Evaluate model performance
Understand whether a model performs well and whether its predictions are reliable.
Improve models
Investigate overfitting, underfitting, feature selection, cross-validation, and hyperparameter tuning.
Apply ML to practical problems
Build solutions for problems involving prediction, classification, segmentation, forecasting, and other analytical tasks.
Learn Machine Learning by Building and Evaluating Solutions.
You will work through practical Machine Learning problems that require you to understand the data, prepare appropriate features, select models, evaluate results, and explain your decisions.
- 01What problem are we trying to solve?
- 02Is this a regression, classification, or clustering problem?
- 03Is the dataset suitable for the problem?
- 04What data quality issues need to be addressed?
- 05Which features are relevant?
- 06Which algorithm is appropriate?
- 07How should the dataset be divided for training and testing?
- 08Which evaluation metrics should we use?
- 09Is the model overfitting or underfitting?
- 10What can we improve?
- 11What limitations should we communicate?
Build and evaluate ML solutions.
You will work on practical Machine Learning projects that demonstrate your ability to approach, build, evaluate, and explain a practical ML solution.
Financial ServicesLoan Default Prediction
Build and evaluate a baseline ML model to flag high-risk loan applications.
TelecommunicationsCustomer Churn Classifier
Compare classification models to predict which customers are likely to churn.
RetailSales Forecasting
Apply time-based modeling to forecast future sales for a retail operation.
From ML foundations to practical model development.
Understand Machine Learning fundamentals and workflow.
Develop Python, NumPy, and Pandas skills.
Work with introductory statistics and probability.
Prepare data: missing values, outliers, encoding, scaling.
Understand supervised learning: regression and classification.
Implement common algorithms: linear regression, logistic regression, trees, ensembles, KNN, SVM.
Explore unsupervised learning: clustering, dimensionality reduction.
Evaluate models: regression and classification metrics.
Investigate overfitting, underfitting, cross-validation, and hyperparameter tuning.
Explain model decisions and limitations.
Complete an end-to-end ML project.
Document and present findings to industry panelists.
Learn Independently. Collaborate. Build Together.
The Machine Learning Study Group uses a three-semester structure to develop technical competence, problem-solving ability, collaboration skills, and confidence in building practical solutions.
Individual Learning
Build a strong technical foundation.
- Understanding Machine Learning fundamentals
- Developing Python and numerical computing skills
- Working with NumPy and Pandas
- Understanding introductory statistics
- Preparing and exploring datasets
- Completing individual exercises and assessments
TeamBud Collaboration
Solve ML challenges as a team.
- Collaborative data preparation
- Feature engineering
- Understanding and selecting algorithms
- Supervised and unsupervised learning exercises
- Reviewing and debugging implementations
- Interpreting model results
- Documenting collaborative solutions
PairBud Collaboration
Apply the full ML workflow as a pair.
- Practical Machine Learning projects
- Problem formulation
- Data preparation and feature engineering
- Model development
- Model evaluation and improvement
- Explaining algorithm selection
- Documenting and presenting project outcomes
Learn Together, Debug Together & Build Better Models.
The weekly review provides an opportunity to connect with Coach Timothy, coaches, and other Study Buddies.
Come with your PC, notebooks, code, questions, and the challenges you encountered during practical activities.
What did we learn during the week?
Which concepts, code implementations, or model results confused learners?
What questions came up, and what alternative approaches can we explore?
Who implemented an interesting solution or developed a useful model?
What did you struggle with, and what did you learn?
Which concepts, implementations, or techniques need more practice?
What are we learning and building next?
Explore the Machine Learning Curriculum.
The curriculum is organized into progressive phases, beginning with Machine Learning foundations and moving through programming, statistics, data preparation, model development, evaluation, and practical projects.
- What is Machine Learning?
- How Machine Learning works
- Why Machine Learning matters
- Applications of Machine Learning
- Traditional programming vs Machine Learning
- Introduction to learning from data
- AI vs ML vs Data Science
- Types of Machine Learning
- Machine Learning workflow
- Problem formulation
What You Should Be Able to Do
The goal is not simply to complete the curriculum or learn how to call different Machine Learning algorithms. It is to develop the technical ability to understand a problem, prepare the data, select an appropriate approach, build a model, evaluate its performance, and improve the solution.
Ready to Build Machine Learning Solutions?
Move beyond learning algorithms. Develop the technical skills to prepare data, build models, evaluate results, and solve practical problems using Machine Learning.
Whether you are strengthening your programming foundation or progressing towards building Machine Learning solutions, the Machine Learning Study Group provides a structured environment to learn, practise, collaborate, and grow.
Understand the concepts. Build the models. Evaluate the results. Improve the solutions.